DILI is a comprehensive repository aimed at enhancing the early detection of Drug-Induced Liver Injury (DILI) through the integration of predicted in vivo and in vitro data. This project utilizes advanced machine learning models and chemical informatics to predict the likelihood of DILI for various compounds. For code see: https://github.com/srijitseal/DILI
You can install the DILI Predictor using pip: pip install dilipred
. Please use Python <3.12, >=3.9
You can also build from source using python-poetry:
- Clone the repository:
git clone https://github.com/Manas02/dili-pip.git
- Navigate to the project directory:
cd dili-pip/
- Install dependencies:
poetry install
- Activate the virtual environment:
poetry shell
- Build the project:
poetry build
To get started with the CLI, use: dili -h
Select from the sidebar to predict DILI for a single molecule.
Here's a basic example of how to use DILIPredictor as a Python library:
from dilipred import DILIPRedictor
if __name__ == '__main__':
dp = DILIPRedictor()
smiles = "CCCCCCCO"
result = dp.predict(smiles)
print(result)
Download key files from https://github.com/srijitseal/DILI/raw/main/local_implementation.zip and run locally!
If you prefer to use the predictor online via Uppsala University SciLifeLab Serve: https://dili.serve.scilifelab.se/
If you prefer to use the predictor online via streamlit: https://dilipredictor.streamlit.app/
If you use DILI Predictor in your work, please cite:
Improved Early Detection of Drug-Induced Liver Injury by Integrating Predicted in vivo and in vitro Data; Srijit Seal, Dominic P. Williams, Layla Hosseini-Gerami, Manas Mahale, Anne E. Carpenter, Ola Spjuth, Andreas Bender bioRxiv 2024.01.10.575128; doi: https://doi.org/10.1101/2024.01.10.575128
This project is licensed under the MIT License. See the LICENSE file for details.
Developed and maintained by Srijit Seal and contributors.
For any questions or issues, please open an issue on the GitHub repository.